I’ll admit it’s a bit odd to talk about the cure before talking about the diagnosis, but as it happens the Welch test is the default t-test in R, so this is probably the best place to discuss it. In t...I’ll admit it’s a bit odd to talk about the cure before talking about the diagnosis, but as it happens the Welch test is the default t-test in R, so this is probably the best place to discuss it. In the Welch test, the “degrees of freedom” doesn’t have to be a whole number anymore, and it doesn’t correspond all that closely to the “number of data points minus the number of constraints” heuristic that we’ve been using up to this point.
I’ll admit it’s a bit odd to talk about the cure before talking about the diagnosis, but as it happens the Welch test is the default t-test in R, so this is probably the best place to discuss it. In t...I’ll admit it’s a bit odd to talk about the cure before talking about the diagnosis, but as it happens the Welch test is the default t-test in R, so this is probably the best place to discuss it. In the Welch test, the “degrees of freedom” doesn’t have to be a whole number any more, and it doesn’t correspond all that closely to the “number of data points minus the number of constraints” heuristic that I’ve been using up to this point.
